Oscillatory Neural Networks for AI Applications in Drones

Neesanth Murugesh; Burak Tanyeri; Bram F. Haverkort; Aida Todri-Sanial

doi:10.1109/ICNSC66229.2025.00029

Oscillatory Neural Networks for AI Applications in Drones

Neesanth Murugesh
, Burak Tanyeri
, Bram F. Haverkort (Corresponding author)
, Aida Todri-Sanial (Corresponding author)

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

147 Downloads (Pure)

Abstract

Artificial Intelligence (AI) in drones has been utilized to perform autonomous operations, including navigation, search and rescue. However, these drones and similar edge devices are power-limited, and traditional deep neural networks require high processing power to process large amounts of data. Oscillatory Neural Networks (ONNs) are an alternative physics-based computing paradigm that enables compact, fast, and low-power computation on the edge via digital implementations. In this paper, a drone fitted with 14 laser-based ranging sensors and an ONN on an FPGA , capable of perceiving the environment, performing pattern retrieval, taking off, landing and avoiding obstacles is presented. An ONN structure comprising two cascaded ONNs for horizontal (lateral) obstacle avoidance and one ONN for vertical (altitude) obstacle avoidance is presented. A response time of 39 ms for the implemented drone is reported, while the average computation time of the ONNs was 139 µs. The power consumed by the ONNs was less than 4% compared to the power consumed by the drone during flight.

Original language	English
Title of host publication	2025 International Conference on Networking, Sensing, and Control, ICNSC 2025
Publisher	Institute of Electrical and Electronics Engineers
Pages	118-125
Number of pages	8
ISBN (Electronic)	979-8-3315-9749-8
DOIs	https://doi.org/10.1109/ICNSC66229.2025.00029
Publication status	Published - 10 Feb 2026
Event	22nd International Conference on Networking, Sensing, and Control (ICNSC) - Oulu, Finland Duration: 1 Oct 2025 → 3 Oct 2025

Conference

Conference	22nd International Conference on Networking, Sensing, and Control (ICNSC)
Abbreviated title	ICNSC 2025
Country/Territory	Finland
City	Oulu
Period	1/10/25 → 3/10/25

Funding

This work has received funding from the European Union's Horizon Europe research and innovation programme, PHASTRAC project under grant agreement No 101092096, European Research Council ERC THERMODON project under grant agreement No. 101125031 and Dutch Research Council's AiNed Fellowship research programme, AI-on-ONN project under grant agreement No. NGF.1607.22.016.

Keywords

3-dimensional Movement
Drone
Obstacle Avoidance
Oscillatory Neural Network

Access to Document

10.1109/ICNSC66229.2025.00029

Oscillatory_Neural_Networks_for_AI_Applications_in_Drones_RevisedFinal author version , 652 KBLicence: CC BY
pdfFinal published version, 681 KBLicence: TAVERNE

Cite this

@inproceedings{ab1d7ac749694a3988916b9b8463fcd0,

title = "Oscillatory Neural Networks for AI Applications in Drones",

abstract = "Artificial Intelligence (AI) in drones has been utilized to perform autonomous operations, including navigation, search and rescue. However, these drones and similar edge devices are power-limited, and traditional deep neural networks require high processing power to process large amounts of data. Oscillatory Neural Networks (ONNs) are an alternative physics-based computing paradigm that enables compact, fast, and low-power computation on the edge via digital implementations. In this paper, a drone fitted with 14 laser-based ranging sensors and an ONN on an FPGA , capable of perceiving the environment, performing pattern retrieval, taking off, landing and avoiding obstacles is presented. An ONN structure comprising two cascaded ONNs for horizontal (lateral) obstacle avoidance and one ONN for vertical (altitude) obstacle avoidance is presented. A response time of 39 ms for the implemented drone is reported, while the average computation time of the ONNs was 139 µs. The power consumed by the ONNs was less than 4\% compared to the power consumed by the drone during flight.",

keywords = "3-dimensional Movement, Drone, Obstacle Avoidance, Oscillatory Neural Network",

author = "Neesanth Murugesh and Burak Tanyeri and Haverkort, \{Bram F.\} and Aida Todri-Sanial",

year = "2026",

month = feb,

day = "10",

doi = "10.1109/ICNSC66229.2025.00029",

language = "English",

pages = "118--125",

booktitle = "2025 International Conference on Networking, Sensing, and Control, ICNSC 2025",

publisher = "Institute of Electrical and Electronics Engineers",

address = "United States",

note = "22nd International Conference on Networking, Sensing, and Control (ICNSC), ICNSC 2025 ; Conference date: 01-10-2025 Through 03-10-2025",

}

Murugesh, N, Tanyeri, B, Haverkort, BF & Todri-Sanial, A 2026, Oscillatory Neural Networks for AI Applications in Drones. in 2025 International Conference on Networking, Sensing, and Control, ICNSC 2025., 11372900, Institute of Electrical and Electronics Engineers, pp. 118-125, 22nd International Conference on Networking, Sensing, and Control (ICNSC), Oulu, Finland, 1/10/25. https://doi.org/10.1109/ICNSC66229.2025.00029

Oscillatory Neural Networks for AI Applications in Drones. / Murugesh, Neesanth; Tanyeri, Burak; Haverkort, Bram F. (Corresponding author) et al.
2025 International Conference on Networking, Sensing, and Control, ICNSC 2025. Institute of Electrical and Electronics Engineers, 2026. p. 118-125 11372900.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Oscillatory Neural Networks for AI Applications in Drones

AU - Murugesh, Neesanth

AU - Tanyeri, Burak

AU - Haverkort, Bram F.

AU - Todri-Sanial, Aida

PY - 2026/2/10

Y1 - 2026/2/10

N2 - Artificial Intelligence (AI) in drones has been utilized to perform autonomous operations, including navigation, search and rescue. However, these drones and similar edge devices are power-limited, and traditional deep neural networks require high processing power to process large amounts of data. Oscillatory Neural Networks (ONNs) are an alternative physics-based computing paradigm that enables compact, fast, and low-power computation on the edge via digital implementations. In this paper, a drone fitted with 14 laser-based ranging sensors and an ONN on an FPGA , capable of perceiving the environment, performing pattern retrieval, taking off, landing and avoiding obstacles is presented. An ONN structure comprising two cascaded ONNs for horizontal (lateral) obstacle avoidance and one ONN for vertical (altitude) obstacle avoidance is presented. A response time of 39 ms for the implemented drone is reported, while the average computation time of the ONNs was 139 µs. The power consumed by the ONNs was less than 4% compared to the power consumed by the drone during flight.

AB - Artificial Intelligence (AI) in drones has been utilized to perform autonomous operations, including navigation, search and rescue. However, these drones and similar edge devices are power-limited, and traditional deep neural networks require high processing power to process large amounts of data. Oscillatory Neural Networks (ONNs) are an alternative physics-based computing paradigm that enables compact, fast, and low-power computation on the edge via digital implementations. In this paper, a drone fitted with 14 laser-based ranging sensors and an ONN on an FPGA , capable of perceiving the environment, performing pattern retrieval, taking off, landing and avoiding obstacles is presented. An ONN structure comprising two cascaded ONNs for horizontal (lateral) obstacle avoidance and one ONN for vertical (altitude) obstacle avoidance is presented. A response time of 39 ms for the implemented drone is reported, while the average computation time of the ONNs was 139 µs. The power consumed by the ONNs was less than 4% compared to the power consumed by the drone during flight.

KW - 3-dimensional Movement

KW - Drone

KW - Obstacle Avoidance

KW - Oscillatory Neural Network

UR - https://www.scopus.com/pages/publications/105034895281

U2 - 10.1109/ICNSC66229.2025.00029

DO - 10.1109/ICNSC66229.2025.00029

M3 - Conference contribution

SP - 118

EP - 125

BT - 2025 International Conference on Networking, Sensing, and Control, ICNSC 2025

PB - Institute of Electrical and Electronics Engineers

T2 - 22nd International Conference on Networking, Sensing, and Control (ICNSC)

Y2 - 1 October 2025 through 3 October 2025

ER -

Oscillatory Neural Networks for AI Applications in Drones

Abstract

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

THERMODON: Thermodynamic-inspired computing with oscillatory neural networks

NGF.1607.22.016 AI-on-ONN Online Learning for Sense-to-Compute Edge AI with Oscillatory Neural Networks

PHASTRAC 101092096 IC:PHASE TRANSITION MATERIALS FORENERGY EFFICIENT EDGE COMPUTING

Cite this

Oscillatory Neural Networks for AI Applications in Drones

Abstract

Conference

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Projects

THERMODON: Thermodynamic-inspired computing with oscillatory neural networks

NGF.1607.22.016 AI-on-ONN Online Learning for Sense-to-Compute Edge AI with Oscillatory Neural Networks

PHASTRAC 101092096 IC:PHASE TRANSITION MATERIALS FORENERGY EFFICIENT EDGE COMPUTING

Cite this